PartImageNet++ Dataset: Enhancing Visual Models with High-Quality Part Annotations

TL;DR

This paper introduces PartImageNet++, a comprehensive dataset with detailed part annotations for ImageNet-1K categories, and proposes a multi-scale recognition model leveraging these annotations to improve object classification and downstream tasks.

Contribution

The paper presents the creation of PartImageNet++, the most extensive dataset with high-quality part annotations, and a novel multi-scale part-supervised recognition model utilizing pseudo labels for enhanced performance.

Findings

Improved object recognition accuracy using part annotations.

Established strong baselines for downstream tasks like segmentation and few-shot learning.

Demonstrated the effectiveness of pseudo labels generated from part annotations.

Abstract

To address the scarcity of high-quality part annotations in existing datasets, we introduce PartImageNet++ (PIN++), a dataset that provides detailed part annotations for all categories in ImageNet-1K. With 100 annotated images per category, totaling 100K images, PIN++ represents the most comprehensive dataset covering a diverse range of object categories. Leveraging PIN++, we propose a Multi-scale Part-supervised recognition Model (MPM) for robust classification on ImageNet-1K. We first trained a part segmentation network using PIN++ and used it to generate pseudo part labels for the remaining unannotated images. MPM then integrated a conventional recognition architecture with auxiliary bypass layers, jointly supervised by both pseudo part labels and the original part annotations. Furthermore, we conducted extensive experiments on PIN++, including part segmentation, object segmentation, and few-shot learning, exploring various ways to leverage part annotations in downstream tasks. Experimental results demonstrated that our approach not only enhanced part-based models for robust object recognition but also established strong baselines for multiple downstream tasks, highlighting the potential of part annotations in improving model performance. The dataset and the code are available at https://github.com/LixiaoTHU/PartImageNetPP.